STAN: Spatio-Temporal Attention Network for Next Location Recommendation

TL;DR

STAN introduces a spatio-temporal attention mechanism for next location recommendation, capturing complex non-adjacent and non-consecutive check-in correlations to improve prediction accuracy.

Contribution

The paper proposes a novel self-attention based model that explicitly models all relevant spatiotemporal relationships in user trajectories for improved location recommendation.

Findings

Outperforms state-of-the-art methods by 9-17%.

Effectively captures non-adjacent location correlations.

Enhances understanding of user movement patterns.

Abstract

The next location recommendation is at the core of various location-based applications. Current state-of-the-art models have attempted to solve spatial sparsity with hierarchical gridding and model temporal relation with explicit time intervals, while some vital questions remain unsolved. Non-adjacent locations and non-consecutive visits provide non-trivial correlations for understanding a user's behavior but were rarely considered. To aggregate all relevant visits from user trajectory and recall the most plausible candidates from weighted representations, here we propose a Spatio-Temporal Attention Network (STAN) for location recommendation. STAN explicitly exploits relative spatiotemporal information of all the check-ins with self-attention layers along the trajectory. This improvement allows a point-to-point interaction between non-adjacent locations and non-consecutive check-ins with explicit spatiotemporal effect. STAN uses a bi-layer attention architecture that firstly aggregates spatiotemporal correlation within user trajectory and then recalls the target with consideration of personalized item frequency (PIF). By visualization, we show that STAN is in line with the above intuition. Experimental results unequivocally show that our model outperforms the existing state-of-the-art methods by 9-17%.